Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    structured data or tables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     of
    0.41
     to
    0.30
     at
    0.28
     građ
    0.25
     silicate
    0.25
     adul
    0.23
     stoichi
    0.23
     adsorbed
    0.23
     on
    0.22
     nutr
    0.22
    POSITIVE LOGITS
    ти
    0.22
    ्टर
    0.21
    ↵
    0.21
    ﾌ
    0.21
     Телефон
    0.20
    РА
    0.20
    也可以
    0.20
     ಶಿವ
    0.20
    也非常
    0.20
    ４
    0.20
    Act Density 0.784%

    No Known Activations